Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ The model was trained from pretrained YOLOv8n weights and fine-tuned on a custom
|
|
| 14 |
* Public kiosks
|
| 15 |
* Smart home media controls
|
| 16 |
* Desktop navigation
|
| 17 |
-
|
| 18 |
# Training Data
|
| 19 |
### Dataset Sources
|
| 20 |
**The training dataset was constructed from two sources:**
|
|
@@ -86,7 +86,7 @@ Dataset availability: https://universe.roboflow.com/b-data-497-ws/hand-gesture-c
|
|
| 86 |
* Limited number of subjects (primarily one person)
|
| 87 |
|
| 88 |
*These factors may affect model generalization.*
|
| 89 |
-
|
| 90 |
# Training Procedure
|
| 91 |
### Framework
|
| 92 |
Training was performed using
|
|
@@ -119,4 +119,5 @@ Base model: YOLOv8n (Nano)
|
|
| 119 |
### Preprocessing Steps
|
| 120 |
* Images resized to 512×512
|
| 121 |
* Bounding box annotations normalized
|
| 122 |
-
* Augmented images generated before training
|
|
|
|
|
|
| 14 |
* Public kiosks
|
| 15 |
* Smart home media controls
|
| 16 |
* Desktop navigation
|
| 17 |
+
***
|
| 18 |
# Training Data
|
| 19 |
### Dataset Sources
|
| 20 |
**The training dataset was constructed from two sources:**
|
|
|
|
| 86 |
* Limited number of subjects (primarily one person)
|
| 87 |
|
| 88 |
*These factors may affect model generalization.*
|
| 89 |
+
***
|
| 90 |
# Training Procedure
|
| 91 |
### Framework
|
| 92 |
Training was performed using
|
|
|
|
| 119 |
### Preprocessing Steps
|
| 120 |
* Images resized to 512×512
|
| 121 |
* Bounding box annotations normalized
|
| 122 |
+
* Augmented images generated before training
|
| 123 |
+
***
|